Training method of HMM input method model of medical document input method model and input method

Abstract

The invention discloses a training method of an HMM input method model of a medical document, the input method model and an input method. The invention is used for solving the problem that the probability of outputting an expected result is very low when a long string of input is encountered during medical term input, and is characterized by comprising the following steps of segmenting words of medical document content for training according to single characters, and counting the probability of each word to serve as the initial state probability of an HMM model; converting all Chinese characters in the medical document for training into corresponding pinyin, and counting the Chinese character corresponding to each pinyin and the respective occurrence probability to serve as the observationstate emission probability of the HMM model; counting the probability that other Chinese characters appear behind each Chinese character in the medical document for training as the hidden state transition probability of the HMM model so that the effect is that the result accuracy of long string input is improved.

Description

technical field [0001] The invention belongs to the field of medical information, and relates to a training method for an HMM input method model of medical documents, an input method model and an input method. Background technique [0002] With the development of medical informatization and intelligence, doctors need to perform more and more text input operations in the office process, such as medical records, doctor's orders and other medical documents. input of. [0003] At present, there are mainly two types of input methods used by most doctors: one is a general-purpose input method, such as Sogou input method, Baidu input method, etc., and the other is a medical input method based on a thesaurus. [0004] Due to the need to input a large number of specialized terms, nouns, and specialist knowledge during the work of doctors, using the existing general-purpose input method will consume a lot of time in the process of manually selecting candidate entries, resulting in lo...

AI Technical Summary

Problems solved by technology

In the pinyin completion process of the above-mentioned common pinyin input method, the probability of outputting the expected result is very low when encountering a long string of input, which affects the doctor's work efficiency

Images